2. DPDK Release 16.11

2.1. New Features

  • Added software parser for packet type.

    • Added a new function rte_pktmbuf_read() to read the packet data from an mbuf chain, linearizing if required.
    • Added a new function rte_net_get_ptype() to parse an Ethernet packet in an mbuf chain and retrieve its packet type from software.
    • Added new functions rte_get_ptype_*() to dump a packet type as a string.
  • Improved offloads support in mbuf.

    • Added a new function rte_raw_cksum_mbuf() to process the checksum of data embedded in an mbuf chain.
    • Added new Rx checksum flags in mbufs to describe more states: unknown, good, bad, or not present (useful for virtual drivers). This modification was done for IP and L4.
    • Added a new Rx LRO mbuf flag, used when packets are coalesced. This flag indicates that the segment size of original packets is known.
  • Added vhost-user dequeue zero copy support.

    The copy in the dequeue path is avoided in order to improve the performance. In the VM2VM case, the boost is quite impressive. The bigger the packet size, the bigger performance boost you may get. However, for the VM2NIC case, there are some limitations, so the boost is not as impressive as the VM2VM case. It may even drop quite a bit for small packets.

    For that reason, this feature is disabled by default. It can be enabled when the RTE_VHOST_USER_DEQUEUE_ZERO_COPY flag is set. Check the VHost section of the Programming Guide for more information.

  • Added vhost-user indirect descriptors support.

    If the indirect descriptor feature is enabled, each packet sent by the guest will take exactly one slot in the enqueue virtqueue. Without this feature, as in the current version, even 64 bytes packets take two slots with Virtio PMD on guest side.

    The main impact is better performance for 0% packet loss use-cases, as it behaves as if the virtqueue size was enlarged, so more packets can be buffered in the case of system perturbations. On the downside, small performance degradations were measured when running micro-benchmarks.

  • Added vhost PMD xstats.

    Added extended statistics to vhost PMD from a per port perspective.

  • Supported offloads with virtio.

    Added support for the following offloads in virtio:

    • Rx/Tx checksums.
    • LRO.
    • TSO.
  • Added virtio NEON support for ARM.

    Added NEON support for ARM based virtio.

  • Updated the ixgbe base driver.

    Updated the ixgbe base driver, including the following changes:

    • Added X550em_a 10G PHY support.
    • Added support for flow control auto negotiation for X550em_a 1G PHY.
    • Added X550em_a FW ALEF support.
    • Increased mailbox version to ixgbe_mbox_api_13.
    • Added two MAC operations for Hyper-V support.
  • Added APIs for VF management to the ixgbe PMD.

    Eight new APIs have been added to the ixgbe PMD for VF management from the PF. The declarations for the API’s can be found in rte_pmd_ixgbe.h.

  • Updated the enic driver.

    • Added update to use interrupt for link status checking instead of polling.
    • Added more flow director modes on UCS Blade with firmware version >= 2.0(13e).
    • Added full support for MTU update.
    • Added support for the rte_eth_rx_queue_count function.
  • Updated the mlx5 driver.

    • Added support for RSS hash results.
    • Added several performance improvements.
    • Added several bug fixes.
  • Updated the QAT PMD.

    The QAT PMD was updated with additional support for:

    • MD5_HMAC algorithm.
    • SHA224-HMAC algorithm.
    • SHA384-HMAC algorithm.
    • GMAC algorithm.
    • KASUMI (F8 and F9) algorithm.
    • 3DES algorithm.
    • NULL algorithm.
    • C3XXX device.
    • C62XX device.
  • Added openssl PMD.

    A new crypto PMD has been added, which provides several ciphering and hashing algorithms. All cryptography operations use the Openssl library crypto API.

  • Updated the IPsec example.

    Updated the IPsec example with the following support:

    • Configuration file support.
    • AES CBC IV generation with cipher forward function.
    • AES GCM/CTR mode.
  • Added support for new gcc -march option.

    The GCC 4.9 -march option supports the Intel processor code names. The config option RTE_MACHINE can be used to pass code names to the compiler via the -march flag.

2.2. Resolved Issues

2.2.1. Drivers

  • enic: Fixed several flow director issues.
  • enic: Fixed inadvertent setting of L4 checksum ptype on ICMP packets.
  • enic: Fixed high driver overhead when servicing Rx queues beyond the first.

2.3. Known Issues

  • L3fwd-power app does not work properly when Rx vector is enabled.

    The L3fwd-power app doesn’t work properly with some drivers in vector mode since the queue monitoring works differently between scalar and vector modes leading to incorrect frequency scaling. In addition, L3fwd-power application requires the mbuf to have correct packet type set but in some drivers the vector mode must be disabled for this.

    Therefore, in order to use L3fwd-power, vector mode should be disabled via the config file.

  • Digest address must be supplied for crypto auth operation on QAT PMD.

    The cryptodev API specifies that if the rte_crypto_sym_op.digest.data field, and by inference the digest.phys_addr field which points to the same location, is not set for an auth operation the driver is to understand that the digest result is located immediately following the region over which the digest is computed. The QAT PMD doesn’t correctly handle this case and reads and writes to an incorrect location.

    Callers can workaround this by always supplying the digest virtual and physical address fields in the rte_crypto_sym_op for an auth operation.

2.4. API Changes

  • The driver naming convention has been changed to make them more consistent. It especially impacts --vdev arguments. For example eth_pcap becomes net_pcap and cryptodev_aesni_mb_pmd becomes crypto_aesni_mb.

    For backward compatibility an alias feature has been enabled to support the original names.

  • The log history has been removed.

  • The rte_ivshmem feature (including library and EAL code) has been removed in 16.11 because it had some design issues which were not planned to be fixed.

  • The file_name data type of struct rte_port_source_params and struct rte_port_sink_params is changed from char * to const char *.

  • Improved device/driver hierarchy and generalized hotplugging.

    The device and driver relationship has been restructured by introducing generic classes. This paves the way for having PCI, VDEV and other device types as instantiated objects rather than classes in themselves. Hotplugging has also been generalized into EAL so that Ethernet or crypto devices can use the common infrastructure.

    • Removed pmd_type as a way of segregation of devices.
    • Moved numa_node and devargs into rte_driver from rte_pci_driver. These can now be used by any instantiated object of rte_driver.
    • Added rte_device class and all PCI and VDEV devices inherit from it
    • Renamed devinit/devuninit handlers to probe/remove to make it more semantically correct with respect to the device <=> driver relationship.
    • Moved hotplugging support to EAL. Hereafter, PCI and vdev can use the APIs rte_eal_dev_attach and rte_eal_dev_detach.
    • Renamed helpers and support macros to make them more synonymous with their device types (e.g. PMD_REGISTER_DRIVER => RTE_PMD_REGISTER_PCI).
    • Device naming functions have been generalized from ethdev and cryptodev to EAL. rte_eal_pci_device_name has been introduced for obtaining unique device name from PCI Domain-BDF description.
    • Virtual device registration APIs have been added: rte_eal_vdrv_register and rte_eal_vdrv_unregister.

2.5. ABI Changes

2.6. Shared Library Versions

The libraries prepended with a plus sign were incremented in this version.

+ librte_cryptodev.so.2
+ librte_eal.so.3
+ librte_ethdev.so.5

2.7. Tested Platforms

  1. SuperMicro 1U
    • BIOS: 1.0c
    • Processor: Intel(R) Atom(TM) CPU C2758 @ 2.40GHz
  2. SuperMicro 1U
    • BIOS: 1.0a
    • Processor: Intel(R) Xeon(R) CPU D-1540 @ 2.00GHz
    • Onboard NIC: Intel(R) X552/X557-AT (2x10G)
      • Firmware-version: 0x800001cf
      • Device ID (PF/VF): 8086:15ad /8086:15a8
    • kernel driver version: 4.2.5 (ixgbe)
  3. SuperMicro 2U
    • BIOS: 1.0a
    • Processor: Intel(R) Xeon(R) CPU E5-4667 v3 @ 2.00GHz
  4. Intel(R) Server board S2600GZ
    • BIOS: SE5C600.86B.02.02.0002.122320131210
    • Processor: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
  5. Intel(R) Server board W2600CR
    • BIOS: SE5C600.86B.02.01.0002.082220131453
    • Processor: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
  6. Intel(R) Server board S2600CWT
    • BIOS: SE5C610.86B.01.01.0009.060120151350
    • Processor: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz
  7. Intel(R) Server board S2600WTT
    • BIOS: SE5C610.86B.01.01.0005.101720141054
    • Processor: Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz
  8. Intel(R) Server board S2600WTT
    • BIOS: SE5C610.86B.11.01.0044.090120151156
    • Processor: Intel(R) Xeon(R) CPU E5-2695 v4 @ 2.10GHz
  9. Intel(R) Server board S2600WTT
    • Processor: Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz
  10. Intel(R) Server
    • Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz
  11. IBM(R) Power8(R)
    • Machine type-model: 8247-22L
    • Firmware FW810.21 (SV810_108)
    • Processor: POWER8E (raw), AltiVec supported

2.8. Tested NICs

  1. Intel(R) Ethernet Controller X540-AT2
    • Firmware version: 0x80000389
    • Device id (pf): 8086:1528
    • Driver version: 3.23.2 (ixgbe)
  2. Intel(R) 82599ES 10 Gigabit Ethernet Controller
    • Firmware version: 0x61bf0001
    • Device id (pf/vf): 8086:10fb / 8086:10ed
    • Driver version: 4.0.1-k (ixgbe)
  3. Intel(R) Corporation Ethernet Connection X552/X557-AT 10GBASE-T
    • Firmware version: 0x800001cf
    • Device id (pf/vf): 8086:15ad / 8086:15a8
    • Driver version: 4.2.5 (ixgbe)
  4. Intel(R) Ethernet Converged Network Adapter X710-DA4 (4x10G)
    • Firmware version: 5.05
    • Device id (pf/vf): 8086:1572 / 8086:154c
    • Driver version: 1.5.23 (i40e)
  5. Intel(R) Ethernet Converged Network Adapter X710-DA2 (2x10G)
    • Firmware version: 5.05
    • Device id (pf/vf): 8086:1572 / 8086:154c
    • Driver version: 1.5.23 (i40e)
  6. Intel(R) Ethernet Converged Network Adapter XL710-QDA1 (1x40G)
    • Firmware version: 5.05
    • Device id (pf/vf): 8086:1584 / 8086:154c
    • Driver version: 1.5.23 (i40e)
  7. Intel(R) Ethernet Converged Network Adapter XL710-QDA2 (2X40G)
    • Firmware version: 5.05
    • Device id (pf/vf): 8086:1583 / 8086:154c
    • Driver version: 1.5.23 (i40e)
  8. Intel(R) Corporation I350 Gigabit Network Connection
    • Firmware version: 1.48, 0x800006e7
    • Device id (pf/vf): 8086:1521 / 8086:1520
    • Driver version: 5.2.13-k (igb)
  9. Intel(R) Ethernet Multi-host Controller FM10000
    • Firmware version: N/A
    • Device id (pf/vf): 8086:15d0
    • Driver version: (fm10k)
  10. Mellanox(R) ConnectX(R)-4 10G MCX4111A-XCAT (1x10G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  11. Mellanox(R) ConnectX(R)-4 10G MCX4121A-XCAT (2x10G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  12. Mellanox(R) ConnectX(R)-4 25G MCX4111A-ACAT (1x25G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  13. Mellanox(R) ConnectX(R)-4 25G MCX4121A-ACAT (2x25G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  14. Mellanox(R) ConnectX(R)-4 40G MCX4131A-BCAT/MCX413A-BCAT (1x40G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  15. Mellanox(R) ConnectX(R)-4 40G MCX415A-BCAT (1x40G)
    • Host interface: PCI Express 3.0 x16
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  16. Mellanox(R) ConnectX(R)-4 50G MCX4131A-GCAT/MCX413A-GCAT (1x50G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  17. Mellanox(R) ConnectX(R)-4 50G MCX414A-BCAT (2x50G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  18. Mellanox(R) ConnectX(R)-4 50G MCX415A-GCAT/MCX416A-BCAT/MCX416A-GCAT (2x50G)
    • Host interface: PCI Express 3.0 x16
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  19. Mellanox(R) ConnectX(R)-4 50G MCX415A-CCAT (1x100G)
    • Host interface: PCI Express 3.0 x16
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  20. Mellanox(R) ConnectX(R)-4 100G MCX416A-CCAT (2x100G)
    • Host interface: PCI Express 3.0 x16
    • Device ID: 15b3:1013
    • MLNX_OFED: 3.4-
    • Firmware version: 12.17.1010
  21. Mellanox(R) ConnectX(R)-4 Lx 10G MCX4121A-XCAT (2x10G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1015
    • MLNX_OFED: 3.4-
    • Firmware version: 14.17.1010
  22. Mellanox(R) ConnectX(R)-4 Lx 25G MCX4121A-ACAT (2x25G)
    • Host interface: PCI Express 3.0 x8
    • Device ID: 15b3:1015
    • MLNX_OFED: 3.4-
    • Firmware version: 14.17.1010

2.9. Tested OSes

  • CentOS 7.2
  • Fedora 23
  • Fedora 24
  • FreeBSD 10.3
  • FreeBSD 11
  • Red Hat Enterprise Linux Server release 6.7 (Santiago)
  • Red Hat Enterprise Linux Server release 7.0 (Maipo)
  • Red Hat Enterprise Linux Server release 7.2 (Maipo)
  • SUSE Enterprise Linux 12
  • Wind River Linux
  • Wind River Linux 8
  • Ubuntu 14.04
  • Ubuntu 15.04
  • Ubuntu 16.04

2.10. Fixes in 16.11 LTS Release

2.10.1. 16.11.1

  • app/test: fix symmetric session free in crypto perf tests
  • app/testpmd: fix check for invalid ports
  • app/testpmd: fix static build link ordering
  • crypto/aesni_gcm: fix IV size in capabilities
  • crypto/aesni_gcm: fix J0 padding bytes
  • crypto/aesni_mb: fix incorrect crypto session
  • crypto/openssl: fix extra bytes written at end of data
  • crypto/openssl: fix indentation in guide
  • crypto/qat: fix IV size in capabilities
  • crypto/qat: fix to avoid buffer overwrite in OOP case
  • cryptodev: fix crash on null dereference
  • cryptodev: fix loop in device query
  • devargs: reset driver name pointer on parsing failure
  • drivers/crypto: fix different auth/cipher keys
  • ethdev: check maximum number of queues for statistics
  • ethdev: fix extended statistics name index
  • ethdev: fix port data mismatched in multiple process model
  • ethdev: fix port lookup if none
  • ethdev: remove invalid function from version map
  • examples/ethtool: fix driver information
  • examples/ethtool: fix querying non-PCI devices
  • examples/ip_pipeline: fix coremask limitation
  • examples/ip_pipeline: fix parsing of pass-through pipeline
  • examples/l2fwd-crypto: fix overflow
  • examples/vhost: fix calculation of mbuf count
  • examples/vhost: fix lcore initialization
  • mempool: fix API documentation
  • mempool: fix stack handler dequeue
  • net/af_packet: fix fd use after free
  • net/bnx2x: fix Rx mode configuration
  • net/cxgbe/base: initialize variable before reading EEPROM
  • net/cxgbe: fix parenthesis on bitwise operation
  • net/ena: fix setting host attributes
  • net/enic: fix hardcoding of some flow director masks
  • net/enic: fix memory leak with oversized Tx packets
  • net/enic: remove unnecessary function parameter attributes
  • net/i40e: enable auto link update for 25G
  • net/i40e: fix Rx checksum flag
  • net/i40e: fix TC bandwidth definition
  • net/i40e: fix VF reset flow
  • net/i40e: fix checksum flag in x86 vector Rx
  • net/i40e: fix crash in close
  • net/i40e: fix deletion of all macvlan filters
  • net/i40e: fix ethertype filter on X722
  • net/i40e: fix link update delay
  • net/i40e: fix logging for Tx free threshold check
  • net/i40e: fix segment number in reassemble process
  • net/i40e: fix wrong return value when handling PF message
  • net/i40e: fix xstats value mapping
  • net/i40evf: fix casting between structs
  • net/i40evf: fix reporting of imissed packets
  • net/ixgbe: fix blocked interrupts
  • net/ixgbe: fix received packets number for ARM
  • net/ixgbe: fix received packets number for ARM NEON
  • net/ixgbevf: fix max packet length
  • net/mlx5: fix RSS hash result for flows
  • net/mlx5: fix Rx packet validation and type
  • net/mlx5: fix Tx doorbell
  • net/mlx5: fix endianness in Tx completion queue
  • net/mlx5: fix inconsistent link status
  • net/mlx5: fix leak when starvation occurs
  • net/mlx5: fix link status query
  • net/mlx5: fix memory leak when parsing device params
  • net/mlx5: fix missing inline attributes
  • net/mlx5: fix updating total length of multi-packet send
  • net/mlx: fix IPv4 and IPv6 packet type
  • net/nfp: fix VLAN offload flags check
  • net/nfp: fix typo in Tx offload capabilities
  • net/pcap: fix timestamps in output pcap file
  • net/qede/base: fix FreeBSD build
  • net/qede: add vendor/device id info
  • net/qede: fix PF fastpath status block index
  • net/qede: fix filtering code
  • net/qede: fix function declaration
  • net/qede: fix per queue statisitics
  • net/qede: fix resource leak
  • net/vhost: fix socket file deleted on stop
  • net/vhost: fix unix socket not removed as closing
  • net/virtio-user: fix not properly reset device
  • net/virtio-user: fix wrongly get/set features
  • net/virtio: fix build without virtio-user
  • net/virtio: fix crash when number of virtio devices > 1
  • net/virtio: fix multiple process support
  • net/virtio: fix performance regression due to TSO
  • net/virtio: fix rewriting LSC flag
  • net/virtio: fix wrong Rx/Tx method for secondary process
  • net/virtio: optimize header reset on any layout
  • net/virtio: store IO port info locally
  • net/virtio: store PCI operators pointer locally
  • net/vmxnet3: fix Rx deadlock
  • pci: fix check of mknod
  • pmdinfogen: fix endianness with cross-compilation
  • pmdinfogen: fix null dereference
  • sched: fix crash when freeing port
  • usertools: fix active interface detection when binding
  • vdev: fix detaching with alias
  • vfio: fix file descriptor leak in multi-process
  • vhost: allow many vhost-user ports
  • vhost: do not GSO when no header is present
  • vhost: fix dead loop in enqueue path
  • vhost: fix guest/host physical address mapping
  • vhost: fix long stall of negotiation
  • vhost: fix memory leak